Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1627 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6654. Min Act: -0.0001

Data Index: 650670 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6559. Min Act: -0.0001

Data Index: 1168721 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6253. Min Act: -0.0001

Data Index: 1602571 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1604891 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6326. Min Act: -0.0001

Data Index: 698252 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6481. Min Act: -0.0001

Data Index: 953944 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1121082 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6241. Min Act: -0.0001

Data Index: 1136263 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5956. Min Act: -0.0001

Data Index: 1016242 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.6120. Min Act: -0.0001

Data Index: 793620 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5701. Min Act: -0.0001

Data Index: 596727 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5879. Min Act: -0.0001

Data Index: 1645296 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5829. Min Act: -0.0001

Data Index: 1553676 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5949. Min Act: -0.0001

Data Index: 1365766 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1410120 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5688. Min Act: -0.0001

Data Index: 1563877 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5689. Min Act: -0.0001

Data Index: 474742 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5474. Min Act: -0.0001

Data Index: 1113867 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5769. Min Act: -0.0001

Data Index: 210994 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.6654. Min Range: -0.6654

Max Act: 0.5599. Min Act: -0.0001

Data Index: 767970 (C4 (Web Text))

Max Activating Token Index: 585